© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61186
    Prev
    Next
    INDEX
    Explanations

    references to bricks or brick-like structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    úÄįast
    -0.07
    er
    -0.07
    ping
    -0.07
    AEA
    -0.07
    osa
    -0.07
    BackingField
    -0.07
    prising
    -0.07
    mlink
    -0.06
    eners
    -0.06
    getAs
    -0.06
    POSITIVE LOGITS
    layers
    0.09
    layer
    0.09
    work
    0.08
    les
    0.07
    aded
    0.07
     naked
    0.07
    workers
    0.07
    nell
    0.06
    yard
    0.06
    elman
    0.06
    Activations Density 0.002%

    No Known Activations